google ads
Search

Everything you need to know about Computed Tomography (CT) & CT Scanning

Kidney: Texture Analysis Imaging Pearls - Educational Tools | CT Scanning | CT Imaging | CT Scan Protocols - CTisus
Imaging Pearls ❯ Kidney ❯ Texture Analysis

-- OR --

  • OBJECTIVE. The purpose of this study is to evaluate the potential value of machine learning (ML)–based high-dimensional quantitative CT texture analysis in predicting the mutation status of the gene encoding the protein polybromo-1 (PBRM1) in patients with clear cell renal cell carcinoma (RCC).
    CONCLUSION. ML-based high-dimensional quantitative CT texture analysis might be a feasible and potential method for predicting PBRM1 mutation status in patients with clear cell RCC.
    Radiogenomics in Clear Cell Renal Cell Carcinoma: Machine Learning–Based High-Dimensional Quantitative CT Texture Analysis in Predicting PBRM1 Mutation Status
    Burak Kocak et al.
    AJR 2019; 212:W55–W63
  • “Quantitative CT (QCT) texture analysis (TA) is an image processing method for measuring repetitive pixel or voxel gray-level patterns that may not be perceptible with the human eye. Several texture parameters can be produced by this method, which makes QCT TA high-dimensional. Although the field of high-dimensional QCT TA is still under development, the literature suggests that QCT TA can be used for characterizing lesions or tumors, predicting staging, nuclear grading, assessing the response to treatment, and predicting survival.”
    Radiogenomics in Clear Cell Renal Cell Carcinoma: Machine Learning–Based High-Dimensional Quantitative CT Texture Analysis in Predicting PBRM1 Mutation Status
    Burak Kocak et al.
    AJR 2019; 212:W55–W63
  • “Radiogenomics is a field of radiology in- vestigating the potential associations be- tween the imaging features of a disease and the underlying genetic patterns or molecular phenotype of that disease. The field has aimed to noninvasively obtain predictive data for diagnostic, prognostic, and, ultimately, optimal therapeutic assessment.”
    Radiogenomics in Clear Cell Renal Cell Carcinoma: Machine Learning–Based High-Dimensional Quantitative CT Texture Analysis in Predicting PBRM1 Mutation Status
    Burak Kocak et al.
    AJR 2019; 212:W55–W63
  • In conclusion, ML-based high-dimensional QCT TA is a feasible and potential method for predicting PBRM1 mutation status in patients with clear cell RCC. Nonetheless, more studies with more labeled data are absolutely required for further validation and improve- ment of the method for clinical use. We hope that the present study will provide the basis for new research.
    Radiogenomics in Clear Cell Renal Cell Carcinoma: Machine Learning–Based High-Dimensional Quantitative CT Texture Analysis in Predicting PBRM1 Mutation Status
    Burak Kocak et al.
    AJR 2019; 212:W55–W63
  • “First-order texture features were extracted by histogram analysis, specifically; Kurtosis (a measure of histogram flatness), Skewness (a measure of histogram asymmetry), and Entropy (a measure of histogram irregularity) as described previously. Manual contouring of tumors was independently repeated in 17% of patients (10/60) for 17 tumors by a second fellowship-trained abdominal radiologist (NS), to assess reproducibility of segmentation.”
    Differentiation of pancreatic neuroendocrine tumors from pancreas renal cell carcinoma metastases on CT using qualitative and quantitative features
    van der Pol CB et al.
    Abdominal Radiology 2019 (in press)
  • “With respect to texture analysis features studied, entropy was significantly higher in PNETs compared to RCC metastases (6.32 ± 0.49 vs. 5.96 ± 0.53, P = 0.004) with a trend towards higher levels of kurtosis and skewness, although the difference in the latter two features did not reach statistical significance between groups (P = 0.067 and 0.099, respectively).”
    Differentiation of pancreatic neuroendocrine tumors from pancreas renal cell carcinoma metastases on CT using qualitative and quantitative features
    van der Pol CB et al.
    Abdominal Radiology 2019 (in press)
  • “The presence of tumor calcification and main pancreatic duct dilation were specific features for PNETs, whereas pancreatic RCC metastases tended to be smaller and were more frequently multiple. PNETs appeared subjectively and quantitatively more heterogeneous using texture analysis. Our results suggest that enhanced CT imaging features may accurately differentiate between PNET and pancreatic RCC metastases which may potentially obviate the need for histological sampling in select cases.”
    Differentiation of pancreatic neuroendocrine tumors from pancreas renal cell carcinoma metastases on CT using qualitative and quantitative features
    van der Pol CB et al.
    Abdominal Radiology 2019 (in press)
  • “Quantitative CT (QCT) texture analysis (TA) is an image processing method for measuring repetitive pixel or voxel gray-level patterns that may not be perceptible with the human eye. Several texture parameters can be produced by this method, which makes QCT TA high-dimensional.”
    Radiogenomics in Clear Cell
    Renal Cell Carcinoma: Machine Learning–Based High-Dimensional Quantitative CT Texture Analysis in Predicting PBRM1 Mutation Status
    Kocak B et al.
    AJR 2019; 212:1–9
  • The second most commonly identified mutation in clear cell RCC involves the tumor suppressor PBRM1 gene. A recent meta-analysis of 2942 patients from seven studies reported that a mutation in PBRM1 or decreased expression of the gene is associated with poor survival, advanced TNM categories and tumor stage, and a higher Fuhrman nuclear grade in patients with RCC.
    Radiogenomics in Clear Cell
    Renal Cell Carcinoma: Machine Learning–Based High-Dimensional Quantitative CT Texture Analysis in Predicting PBRM1 Mutation Status
    Kocak B et al.
    AJR 2019; 212:1–9
  • “In the present study, we investigated the potential value of ML-based high-dimensional QCT TA in predicting the PBRM1 mutation status of patients with clear cell RCC. The results of our study suggest that high-dimensional QCT TA using different ML classifiers (ANN and RF algorithms) has potential in distinguishing clear cell RCCs with and without the PBRM1 mutation. “
    Radiogenomics in Clear Cell
    Renal Cell Carcinoma: Machine Learning–Based High-Dimensional Quantitative CT Texture Analysis in Predicting PBRM1 Mutation Status
    Kocak B et al.
    AJR 2019; 212:1–9
  • “In conclusion, ML-based high-dimension- al QCT TA is a feasible and potential method for predicting PBRM1 mutation status in patients with clear cell RCC. Nonetheless, more studies with more labeled data are absolutely required for further validation and improvement of the method for clinical use. We hope that the present study will provide the basis for new research.”
    Radiogenomics in Clear Cell
    Renal Cell Carcinoma: Machine Learning–Based High-Dimensional Quantitative CT Texture Analysis in Predicting PBRM1 Mutation Status
    Kocak B et al.
    AJR 2019; 212:1–9
  • “CT texture features (in particular, entropy, the mean of positive pixels, and the SD of the pixel distribution histogram) are associated with tumor histologic findings, nuclear grade, and outcome measures. The contrast phase does seem to affect heterogeneity measures.”


    CT Textural Analysis of Large Primary Renal Cell Carcinomas: Pretreatment Tumor Heterogeneity Correlates With Histologic Findings and Clinical Outcomes 
Lubner MG et al
AJR 2016; 207:96–105
  • “CT texture analysis can be used to accurately differentiate fp-AML from RCC on unenhanced CT images.”

    Can Quantitative CT Texture Analysis be Used to Differentiate Fat-poor Renal Angiomyolipoma from Renal Cell Carcinoma on Unenhanced CT Images?
    Hodgdon T et al.
    Radiology. 2015 Apr 23:142215. [Epub ahead of print
  • “CTTA software was used to analyze 20 clear cell renal cell carcinomas, 20 papillary renal cell carcinomas, 20 oncocytomas, and 20 renal cysts.  Regions of interest were drawn around each mass on multiple slices in the arterial, venous, and delayed phases on renal mass protocol CT scans. Unfiltered images and spatial band-pass filtered images were analyzed to quantify heterogeneity.  Random forest method was used to construct a predictive model to classify lesions using quantitative parameters.”
    CT Texture Analysis of Renal Masses:
     Pilot study utilizing random forest classification for prediction of pathology
    Raman SP, Chen Y, Schroeder JL,Huang P, Fishman EK
    Academic Radiol (in press)
  • “The random forest model correctly categorized oncocytomas in 89% of cases (sensitivity=89%, specificity=99%), clear cell renal cell carcinomas in 91% of cases (sensitivity=91%, specificity=97%), cysts in 100% of cases (sensitivity=100%, specificity=100%), and papillary renal cell carcinomas in 100% of cases (sensitivity=100%, specificity=98%).”
    CT Texture Analysis of Renal Masses:
     Pilot study utilizing random forest classification for prediction of pathology
    Raman SP, Chen Y, Schroeder JL,Huang P, Fishman EK
    Academic Radiol (in press)
  • Renal Mass Analysis
© 1999-2019 Elliot K. Fishman, MD, FACR. All rights reserved.